SOTAVerified

Image Super-Resolution

Image Super-Resolution is a machine learning task where the goal is to increase the resolution of an image, often by a factor of 4x or more, while maintaining its content and details as much as possible. The end result is a high-resolution version of the original image. This task can be used for various applications such as improving image quality, enhancing visual detail, and increasing the accuracy of computer vision algorithms.

Papers

Showing 110 of 1589 papers

TitleStatusHype
SpectraLift: Physics-Guided Spectral-Inversion Network for Self-Supervised Hyperspectral Image Super-Resolution0
IM-LUT: Interpolation Mixing Look-Up Tables for Image Super-ResolutionCode1
Efficient Feedback Gate Network for Hyperspectral Image Super-Resolution0
Unsupervised Image Super-Resolution Reconstruction Based on Real-World Degradation Patterns0
Efficient Star Distillation Attention Network for Lightweight Image Super-Resolution0
Structural Similarity-Inspired Unfolding for Lightweight Image Super-ResolutionCode1
Stroke-based Cyclic Amplifier: Image Super-Resolution at Arbitrary Ultra-Large Scales0
Incorporating Uncertainty-Guided and Top-k Codebook Matching for Real-World Blind Image Super-Resolution0
Task-driven real-world super-resolution of document scans0
Practical Manipulation Model for Robust Deepfake DetectionCode0
Show:102550
← PrevPage 1 of 159Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1HMA†PSNR35.24Unverified
2DRCT-LPSNR35.17Unverified
3Hi-IR-LPSNR35.16Unverified
4HAT-LPSNR35.09Unverified
5HAT_FIRPSNR34.94Unverified
6CPAT+PSNR34.89Unverified
7HATPSNR34.81Unverified
8CPATPSNR34.76Unverified
9SwinFIRPSNR34.57Unverified
10DRCTPSNR34.54Unverified